From 4288c623d62cf90d8e4444facb3379fb06d01140 Mon Sep 17 00:00:00 2001 From: "Gregory P. Smith" Date: Thu, 20 Jul 2023 20:30:52 -0700 Subject: [PATCH] [3.12] gh-106669: Revert "gh-102988: Detect email address parsing errors ... (GH-105127)" (GH-106733) This reverts commit 18dfbd035775c15533d13a98e56b1d2bf5c65f00. Adds a regression test from the issue. See https://github.com/python/cpython/issues/106669.. (cherry picked from commit a31dea1feb61793e48fa9aa5014f358352205c1d) Co-authored-by: Gregory P. Smith --- Doc/library/email.utils.rst | 24 --- Lib/email/test/test_email.py | 18 ++ Lib/email/test/test_email_renamed.py | 4 Lib/email/utils.py | 66 ---------- Misc/NEWS.d/next/Security/2023-06-13-20-52-24.gh-issue-102988.Kei7Vf.rst | 5 5 files changed, 32 insertions(+), 85 deletions(-) create mode 100644 Misc/NEWS.d/next/Security/2023-06-13-20-52-24.gh-issue-102988.Kei7Vf.rst --- a/Doc/library/email.utils.rst +++ b/Doc/library/email.utils.rst @@ -63,11 +63,6 @@ There are several useful utilities provi :func:`time.mktime`; otherwise ``None`` will be returned. Note that indexes 6, 7, and 8 of the result tuple are not usable. - .. versionchanged:: 3.12 - For security reasons, addresses that were ambiguous and could parse into - multiple different addresses now cause ``('', '')`` to be returned - instead of only one of the *potential* addresses. - .. function:: parsedate_tz(date) @@ -108,25 +103,6 @@ There are several useful utilities provi .. versionadded:: 2.4 - When parsing fails for a single fieldvalue, a 2-tuple of ``('', '')`` - is returned in its place. Other errors in parsing the list of - addresses such as a fieldvalue seemingly parsing into multiple - addresses may result in a list containing a single empty 2-tuple - ``[('', '')]`` being returned rather than returning potentially - invalid output. - - Example malformed input parsing: - - .. doctest:: - - >>> from email.utils import getaddresses - >>> getaddresses(['alice@example.com ', 'me@example.com']) - [('', '')] - - .. versionchanged:: 3.12 - The 2-tuple of ``('', '')`` in the returned values when parsing - fails were added as to address a security issue. - .. function:: make_msgid([idstring]) --- a/Lib/email/test/test_email.py +++ b/Lib/email/test/test_email.py @@ -2414,6 +2414,24 @@ Foo [('Al Person', 'aperson@dom.ain'), ('Bud Person', 'bperson@dom.ain')]) + def test_getaddresses_comma_in_name(self): + """GH-106669 regression test.""" + self.assertEqual( + Utils.getaddresses( + [ + '"Bud, Person" ', + 'aperson@dom.ain (Al Person)', + '"Mariusz Felisiak" ', + ] + ), + [ + ('Bud, Person', 'bperson@dom.ain'), + ('Al Person', 'aperson@dom.ain'), + ('Mariusz Felisiak', 'to@example.com'), + ], + ) + + @unittest.skip("Results are too irregular with patches for CVE-2023-27043") def test_getaddresses_nasty(self): eq = self.assertEqual eq(Utils.getaddresses(['foo: ;']), [('', '')]) --- a/Lib/email/test/test_email_renamed.py +++ b/Lib/email/test/test_email_renamed.py @@ -2275,12 +2275,14 @@ Foo [('Al Person', 'aperson@dom.ain'), ('Bud Person', 'bperson@dom.ain')]) + @unittest.skip("Results are too irregular with patches for CVE-2023-27043") def test_getaddresses_nasty(self): eq = self.assertEqual eq(utils.getaddresses(['foo: ;']), [('', '')]) eq(utils.getaddresses( ['[]*-- =~$']), - [('', ''), ('', ''), ('', '*--')]) + [('', ''), ('', ''), ('', '*--')] + ) eq(utils.getaddresses( ['foo: ;', '"Jason R. Mastaler" ']), [('', ''), ('Jason R. Mastaler', 'jason@dom.ain')]) --- a/Lib/email/utils.py +++ b/Lib/email/utils.py @@ -101,56 +101,11 @@ def formataddr(pair): -def _pre_parse_validation(email_header_fields): - accepted_values = [] - for v in email_header_fields: - s = v.replace('\\(', '').replace('\\)', '') - if s.count('(') != s.count(')'): - v = "('', '')" - accepted_values.append(v) - - return accepted_values - - - -def _post_parse_validation(parsed_email_header_tuples): - accepted_values = [] - # The parser would have parsed a correctly formatted domain-literal - # The existence of an [ after parsing indicates a parsing failure - for v in parsed_email_header_tuples: - if '[' in v[1]: - v = ('', '') - accepted_values.append(v) - - return accepted_values - - - def getaddresses(fieldvalues): - """Return a list of (REALNAME, EMAIL) or ('','') for each fieldvalue. - - When parsing fails for a fieldvalue, a 2-tuple of ('', '') is returned in - its place. - - If the resulting list of parsed address is not the same as the number of - fieldvalues in the input list a parsing error has occurred. A list - containing a single empty 2-tuple [('', '')] is returned in its place. - This is done to avoid invalid output. - """ - fieldvalues = [str(v) for v in fieldvalues] - fieldvalues = _pre_parse_validation(fieldvalues) - all = COMMASPACE.join(v for v in fieldvalues) + """Return a list of (REALNAME, EMAIL) for each fieldvalue.""" + all = COMMASPACE.join(str(v) for v in fieldvalues) a = _AddressList(all) - result = _post_parse_validation(a.addresslist) - - n = 0 - for v in fieldvalues: - n += v.count(',') + 1 - - if len(result) != n: - return [('', '')] - - return result + return a.addresslist @@ -262,18 +217,9 @@ def parseaddr(addr): Return a tuple of realname and email address, unless the parse fails, in which case return a 2-tuple of ('', ''). """ - if isinstance(addr, list): - addr = addr[0] - - if not isinstance(addr, str): - return ('', '') - - addr = _pre_parse_validation([addr])[0] - addrs = _post_parse_validation(_AddressList(addr).addresslist) - - if not addrs or len(addrs) > 1: - return ('', '') - + addrs = _AddressList(addr).addresslist + if not addrs: + return '', '' return addrs[0] --- a/Misc/NEWS.d/next/Security/2023-06-13-20-52-24.gh-issue-102988.Kei7Vf.rst +++ b/Misc/NEWS.d/next/Security/2023-06-13-20-52-24.gh-issue-102988.Kei7Vf.rst @@ -1,3 +1,8 @@ +Reverted the :mod:`email.utils` security improvement change released in +3.12beta4 that unintentionally caused :mod:`email.utils.getaddresses` to fail +to parse email addresses with a comma in the quoted name field. +See :gh:`106669`. + CVE-2023-27043: Prevent :func:`email.utils.parseaddr` and :func:`email.utils.getaddresses` from returning the realname portion of an invalid RFC2822 email header in the email address portion of the 2-tuple